Borrowing it
Nothing to install: this file belongs to KCNyu/clawock. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/KCNyu/clawock/master/AGENTS.mdgit clone --depth 1 https://github.com/KCNyu/clawockWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kcnyu/clawock/agents-md)<a href="https://agentmods.dev/instructions/kcnyu/clawock/agents-md"><img src="https://agentmods.dev/badge/instructions/kcnyu/clawock/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kcnyu/clawock/agents-md"><img src="https://agentmods.dev/badge/instructions/kcnyu/clawock/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02765 | $0.02765 |
| Opus 5.5 | $0.01106 | $0.01106 |
| Sonnet 5.5 | $0.00553 | $0.00553 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
clawock AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for every agent in this repository: the OpenClaw investment assistant
(Rick, see IDENTITY.md) and the coding agents (Claude Code, Codex, OpenCode, dsh).
CLAUDE.md only bridges here. Humans read README.md and docs/README.md.
Session start
OpenClaw injects the bootstrap files for the session profile. Use what is already in context; do not read an injected file again.
- Direct chat:
SOUL.md,IDENTITY.md,USER.md,TOOLS.md,HEARTBEAT.mdandMEMORY.mdare injected. KeepMEMORY.mdout of group and shared contexts. - Isolated cron and subagent runs: follow the job payload and its skill.
MEMORY.mdis not injected there, so a rule a scheduled run must obey belongs in the payload, the skill mode or a postflight gate. - Investment question: follow
INVESTMENT_SOP.mdand the skillTOOLS.mdroutes to. - Ordinary chat: answer with known context. Load holdings, cron or repository state only when the question needs it.
- Coding work: no persona, SOP or holdings reads. Start at § Code changes.
Delegation
- A request naming Claude Code (Claude/claudecode), Codex, OpenCode or dsh as the actor
("让 claudecode 看看…", "have Codex fix…") is explicit delegation, even for a small task
and without words such as "委派" or "后台跑". Use the
agent-dispatchskill and return once the dispatch succeeded. The named worker is distinct from the main session even when both use the same model family. - Forward the request with known context. Look up only missing routing facts; the worker inspects code, issues and CI.
- "你直接做 / 当前会话做 / 不要委派" ("do it here / no delegation") overrides this routing. A request to investigate or optimize together stays in the current conversation.
- A dispatched worker (
AGENT_DISPATCH_TASK_IDset, or a 【派发约定】 block in its prompt) finishes its own task and does not dispatch it again.
Commands
Runtime commands are the installed clawock entry points; source is src/clawock/.
Host, publishing, CI and growth wiring lives under ops/. Parameters:
docs/reference/commands.md. Skill routing: TOOLS.md § Skill 路由表.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · +1 lines · +28 tokens per session a5bbd7026a53
- 5d ago Changed · +6 tokens per session 7312774d984c
- 18d ago Changed · +9 lines · -33 tokens per session da8eb427c59d
- 19d ago Changed · +4 lines · +70 tokens per session 53e701b43fd2
- 22d ago Changed · +14 lines · +193 tokens per session 4a7ebfe9e4ac
- 25d ago Changed · +1 lines · +18 tokens per session 28e98acc2bec
- 29d ago Changed · +1 lines · +22 tokens per session 3611fc3ff91b
- 1mo ago Changed · +16 lines · +321 tokens per session 7dd13af47b3f
- 1mo ago First seen · 154 lines · 2,140 tokens per session scan A d32811d144d4
clawock AGENTS.md is an instructions file published in the GitHub repository KCNyu/clawock (21 stars, last pushed today), licensed MIT. It adds 2,765 tokens to every session, about $0.0111 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.